© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 55383
    Prev
    Next
    INDEX
    Explanations

    phrases with 'for', 'to', 'in', 'and'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IS
    0.46
    ears
    0.43
     beverages
    0.41
    ীয়
    0.41
    ijs
    0.41
    ΙΑ
    0.40
    ADDING
    0.40
    ῖ
    0.40
     seis
    0.40
    anyakan
    0.39
    POSITIVE LOGITS
     The
    0.50
    นี่
    0.42
     Św
    0.41
    䏍
    0.39
     это
    0.38
     חי
    0.38
     DeS
    0.37
     Atem
    0.37
     SCP
    0.37
     લા
    0.37
    Activations Density 0.014%

    No Known Activations